Real-time monitoring and evaluation of muscle atrophy are vital for efficient treatment and effective diagnosis. Although some systems have been developed to monitor loss of muscle mass or strength, they are bulky and nonspecific, cannot be applied to the body, and cannot assess the degree of muscle atrophy. Our research focuses on developing a wireless multisensor wearable system (WMWS) for on-body monitoring and assessment of atrophy, which utilizes a single-electrode triboelectric nanogenerator (S-TENG) and electrochemical creatinine (CREA) sensor to achieve real-time acquisition of plantar pressure and interstitial fluid (ISF) CREA concentration. In addition, LSTM (long short-term memory) and SVM (support vector machine) machine learning (ML) algorithms also prove that our multisensor strategy can effectively improve the recognition rate of different degrees of atrophy (the highest accuracy reached 92.32%). Overall, our work makes it possible to monitor and grade muscle atrophy remotely in real time.